Sep 25 00:22 gen-cards: regenerate Use-it block Sep 24 05:06 gen-cards: regenerate Use-it block Sep 14 18:38 Card: macOS/iOS 27 GA wording (beta requirement dropped; beta findings dated) 16:48 granite_4_0_h_350m_decode_fp16: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py Sep 7 10:48 gen-cards: regenerate Use-it block 10:43 Card: DeviceMark row (2026-09) Sep 6 18:02 Card metadata: library_name coreai, ensure coreai tag Sep 5 04:16 Card: definition line (Core AI, 2026-09) Sep 4 15:22 Card: base_model_relation: quantized (so the conversion lists under the base model's Quantizations, not Finetunes) 08:10 Card: Apple Silicon / hybrid tags and a one-line measured summary under the title (agent-discoverability) Aug 25 03:23 gen-cards: regenerate Use-it block Aug 15 05:15 Link the card back to its collection and the request box Jul 24 00:41 gen-cards: regenerate Use-it block Jul 17 20:05 Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure); gated token-for-token vs fp32 oracle 20:00 Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure); gated token-for-token vs fp32 oracle Jul 14 23:53 Note b2 (beta3-loadable) bundles under gpu-pipelined-b2/ 23:32 Add b2 (beta3-loadable) bundle under gpu-pipelined-b2/granite_4_0_h_1b_decode_int8hu_block32_sym/ (b1 retained) Jul 2 17:45 gen-cards: regenerate Use-it block 15:11 gen-cards: regenerate Use-it block 13:34 gen-cards: add Use-it markers Jun 12 08:49 Add root config.json (Hub download-stats query file + framework pointer) Jun 11 04:27 int8hu device-ship bundle row (+17-21% iPhone); per-channel delegate-bug note 04:26 Upload folder using huggingface_hub 00:08 add granite_4_0_h_350m_decode_fp16 LanguageBundle 00:08 add granite_4_0_h_1b_decode_int8lin LanguageBundle 00:06 Upload LICENSE with huggingface_hub 00:06 Upload README.md with huggingface_hub 00:06 initial commit 
